相关论文: BrainWash: A Poisoning Attack to Forget in Continu…

Traditional machine learning systems were designed in a centralized manner. In such designs, the central entity maintains both the machine learning model and the data used to adjust the model's parameters. As data centralization yields…

As a fundamental issue in lifelong learning, catastrophic forgetting is directly caused by inaccessible historical data; accordingly, if the data (information) were memorized perfectly, no forgetting should be expected. Motivated by that,…

Knowledge distillation has become a cornerstone in modern machine learning systems, celebrated for its ability to transfer knowledge from a large, complex teacher model to a more efficient student model. Traditionally, this process is…

Catastrophic forgetting is a critical challenge in training deep neural networks. Although continual learning has been investigated as a countermeasure to the problem, it often suffers from the requirements of additional network components…

Federated Learning has been introduced as a new machine learning paradigm enhancing the use of local devices. At a server level, FL regularly aggregates models learned locally on distributed clients to obtain a more general model. Current…

Lifelong learning is challenging for deep neural networks due to their susceptibility to catastrophic forgetting. Catastrophic forgetting occurs when a trained network is not able to maintain its ability to accomplish previously learned…

Catastrophic forgetting is the notorious vulnerability of neural networks to the change of the data distribution while learning. This phenomenon has long been considered a major obstacle for allowing the use of learning agents in realistic…

Current deep learning methods are regarded as favorable if they empirically perform well on dedicated test sets. This mentality is seamlessly reflected in the resurfacing area of continual learning, where consecutively arriving data is…

Manipulation of local training data and local updates, i.e., the poisoning attack, is the main threat arising from the collaborative nature of the federated learning (FL) paradigm. Most existing poisoning attacks aim to manipulate local…

Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…

The rapid progress of AI, combined with its unprecedented public adoption and the propensity of large neural networks to memorize training data, has given rise to significant data privacy concerns. To address these concerns, machine…

Federated Learning (FL) is susceptible to poisoning attacks, wherein compromised clients manipulate the global model by modifying local datasets or sending manipulated model updates. Experienced defenders can readily detect and mitigate the…

Humans have a remarkable ability to quickly and effectively learn new concepts in a continuous manner without forgetting old knowledge. Though deep learning has made tremendous successes on various computer vision tasks, it faces challenges…

Poisoning attacks on machine learning systems compromise the model performance by deliberately injecting malicious samples in the training dataset to influence the training process. Prior works focus on either availability attacks (i.e.,…

As in-the-wild data are increasingly involved in the training stage, machine learning applications become more susceptible to data poisoning attacks. Such attacks typically lead to test-time accuracy degradation or controlled misprediction.…

Advances in deep learning, combined with availability of large datasets, have led to impressive improvements in face presentation attack detection research. However, state-of-the-art face antispoofing systems are still vulnerable to novel…

While numerous defense methods have been proposed to prohibit potential poisoning attacks from untrusted data sources, most research works only defend against specific attacks, which leaves many avenues for an adversary to exploit. In this…

Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms…

The pursuit of long-term autonomy mandates that machine learning models must continuously adapt to their changing environments and learn to solve new tasks. Continual learning seeks to overcome the challenge of catastrophic forgetting,…

Continually learning in the real world must overcome many challenges, among which noisy labels are a common and inevitable issue. In this work, we present a repla-ybased continual learning framework that simultaneously addresses both…